Radar / AI infrastructure / NVIDIA Run:ai open source GPU orchestration…
NVIDIA Run:ai open source GPU orchestration platform
In today's Spotlight · Picked by 2 of 3 modelsNVIDIA made its GPU-sharing software free and open, so teams can pool expensive chips without paid licences.Like a booking system for shared equipment.
NVIDIA open-sourced the full Run:ai platform for AI workload and GPU orchestration on Kubernetes, plus four standalone components.
Why it matters
The software that decides how GPUs are shared in AI factories is now open source, with a free Community Product and no paid subscription required.
What you could build with it
A small cloud provider could build a multi-tenant GPU cloud on the open Run:ai platform, offering fractional-GPU rentals to indie developers who cannot afford whole GPUs.
Does it hold up?
Usable now for operators: eight partners shipped integrations on day one and a Helm chart installs the Community Product, though enterprise support is not included.
Built with NVIDIA Run:ai open source GPU orchestration…
- vCluster Labs Turns Open-Source NVIDIA Run:ai Into a Managed Cluster Productarticle · vCluster announced managed Run:ai clusters on the open-source release, with per-tenant isolation and no commercial NVIDIA Run:ai license required.
- Mirantis Integrates Open-Source NVIDIA Run:ai with k0rdent AIarticle · Mirantis integrated the open-source Run:ai into k0rdent AI for full-stack lifecycle management from bare metal to GPU orchestration.
Learn more
First spotted on article: source.
More AI infrastructure
DeepGEMM: DeepSeek's open GPU BLAS kernel libraryDeepSeek's DeepGEMM, a clean and efficient open-source BLAS kernel library for NVIDIA GPUs (up to 1550 TFLOPS on…infra · JEV 0.77OpenViking — self-evolving context database for AI agentsByteDance Volcengine's open-source (AGPL-3.0) context database that unifies agent memory, knowledge RAG, and skills…infra · JEV 0.76Modular open-sources MAX inference server, Mojo stdlib and accelerator kernelsThe core of Modular's unified AI deployment stack is now open: the MAX inference server (OpenAI-compatible endpoints)…infra · JEV 0.76OmniRouteFree MIT AI gateway: one endpoint, 290+ providers and 500+ models with quota-aware auto-fallback.infra · JEV 0.75Context Mode: context-window optimization for AI coding agentsMCP server for AI coding agents that sandboxes verbose tool output and persists session memory, cutting context use by…infra · JEV 0.74StrataOpen-source inference engine that runs the 125B-parameter Qwen3.8-Flash-Next MoE on a single consumer GPU with 12GB+…infra · JEV 0.74
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.